Self-supervised and Interpretable Data Cleaning with Sequence Generative Adversarial Networks
Summary: Garf: a SeqGAN-based, self-supervised framework that extracts interpretable conditional repair rules (e.g., city→county) directly from noisy tables. A generator plus two discriminators (D to learn dependencies, D' to iteratively refine rules/data) yields interpretable, high-accuracy cleaning without labeled data. (summarized by gpt-5-mini on Feb 09 2026)
Incoming Non-self Citations Over Time
Authors
- 1. Jinfeng Peng (Northeastern University, China)
- 2. Derong Shen (Northeastern University, China)
- 3. Nan Tang (Hong Kong Baptist University; Qatar Computing Research Institute)
- 4. Tieying Liu (Northeastern University, China)
- 5. Yue Kou (Northeastern University, China)
- 6. Tiezheng Nie (Northeastern University, China)
- 7. Hang Cui (University of Illinois Urbana-Champaign)
- 8. Ge Yu (Northeastern University, China)
BibTeX Citation
@article{peng_vldb23,
title = {{Self-supervised and Interpretable Data Cleaning with Sequence Generative Adversarial Networks}},
author = {Peng, Jinfeng and Shen, Derong and Tang, Nan and Liu, Tieying and Kou, Yue and Nie, Tiezheng and Cui, Hang and Yu, Ge},
journal = {PVLDB},
series = {{VLDB} '23},
volume = {16},
number = {3},
pages = {433--446},
doi = {10.14778/3570690.3570694},
url = {https://doi.org/10.14778/3570690.3570694},
year = {2023}
}Incoming Citations (Sorted by Pagerank)
Showing 7 of 7 citing papers.
| Rank | Citing Paper | Year | Venue | Pagerank |
|---|---|---|---|---|
| 8,049 | TSM-Bench: Benchmarking Time Series Database Systems for Monitoring Applications | 2023 | VLDB | 5.3841015e-05 |
| 9,634 | GIDCL: A Graph-Enhanced Interpretable Data Cleaning Framework with Large Language Models | 2024 | SIGMOD | 5.1354312e-05 |
| 10,218 | In-Database Data Imputation | 2024 | SIGMOD | 5.0461625e-05 |
| 10,592 | Understanding the Impact of Data Noise in Federated Learning: [Experiments & Analysis] | 2026 | SIGMOD | 4.9605343e-05 |
| 11,268 | The Best of Both Worlds: On Repairing Timestamps and Attribute Values for Multivariate Time Series | 2025 | SIGMOD | 4.9605343e-05 |
| 11,686 | SEER: An End-to-End Toolkit for Benchmarking Time Series Database Systems in Monitoring Applications | 2024 | VLDB | 4.9605343e-05 |
| 11,713 | Generalizable Data Cleaning of Tabular Data in Latent Space | 2024 | VLDB | 4.9605343e-05 |
Previous
Page 1 / 1
Next
Outgoing Citations (Sorted by Pagerank)
Showing 25 of 25 cited papers.
Citations counted here include only citations to other VLDB/SIGMOD/CIDR/PODS papers in this database.
Previous
Page 1 / 1
Next
Semantically Similar Papers
| # | Overall Rank | Paper | Year | Venue |
|---|---|---|---|---|
| 1 | 9,094 | DAFDiscover: Robust Mining Algorithm for Dynamic Approximate Functional Dependencies on Dirty Data | 2024 | VLDB |
| 2 | 989 | Data Cleaning: Overview and Emerging Challenges | 2016 | SIGMOD |
| 3 | 4,978 | Adaptive Data Augmentation for Supervised Learning over Missing Data | 2021 | VLDB |
| 4 | 9,634 | GIDCL: A Graph-Enhanced Interpretable Data Cleaning Framework with Large Language Models | 2024 | SIGMOD |
| 5 | 2,958 | Towards Dependable Data Repairing with Fixing Rules | 2014 | SIGMOD |
| 6 | 9,263 | Auto-Test: Learning Semantic-Domain Constraints for Unsupervised Error Detection in Tables | 2025 | SIGMOD |
| 7 | 7,884 | Learning Over Dirty Data Without Cleaning | 2020 | SIGMOD |
| 8 | 3,277 | Automatic Data Repair: Are We Ready to Deploy? | 2024 | VLDB |
| 9 | 11,713 | Generalizable Data Cleaning of Tabular Data in Latent Space | 2024 | VLDB |
| 10 | 5,501 | Semi-Supervised Data Cleaning with Raha and Baran | 2021 | CIDR |